面试题库

全部 Django Elasticsearch FastAPI Flask Function Call JVM Java IO Java 后端 Java 基础 Java 并发 Java 新特性 Java 集合 JavaWeb Kafka LLM LangChain LangGraph MongoDB MyBatis MySQL Netty Nginx Python RAG RabbitMQ Redis RocketMQ Spring Spring AI SpringBoot SpringCloud SpringMVC ZooKeeper 分布式 后端技术 大厂面经 大数据 微服务 提示词工程 操作系统 数据库 数据结构 智能体 海康威视2026秋季社招专项 消息队列 监控运维 算法 系统设计 缓存 计算机基础 计算机网络 设计模式 面试题 高可用 高并发
RAG 中等

Explain the steps in the indexing process in a RAG pipeline

作答 →
RAG 中等

Can you give examples of real-world applications where RAG systems have demonstrated value?

作答 →
RAG 中等

Explain the pros and cons of semantic chunking

作答 →
RAG 中等

What are the criteria to choose a specific chunking method in RAG?

作答 →
RAG 中等

What are some common chunking methods used in RAG?

作答 →
RAG 中等

What are the fundamental challenges of RAG systems?

作答 →
RAG 中等

Is RAG still relevant in the era of long context LLMs?

作答 →
RAG 中等

Explain why RAG is required when LLMs are already powerful

作答 →
RAG 中等

In what situations would you prioritize Context Precision over Context Recall in a RAG retriever, and how would this impact the generator’s performance?

作答 →
RAG 中等

If your retriever achieves high context precision but low context recall, what types of user queries would likely suffer most?

作答 →
RAG 中等

In a RAG pipeline, how might context recall impact the completeness of generated answers? Describe a scenario illustrating this relationship

作答 →
RAG 中等

What happens with a weak retriever in Retrieval-Augmented Generation (RAG) systems?

作答 →